Explainability in Deep Reinforcement Learning: A Review into Current Methods and Applications

被引：16

作者：

Hickling, Thomas ^{[1
]}

Zenati, Abdelhafid ^{[1
]}

Aouf, Nabil ^{[1
]}

Spencer, Phillippa ^{[2
]}

机构：

[1] City Univ London, Dept Elect Engn, Northampton Sq, London EC1V 0HB, England

[2] Def Sci & Technol Lab Dstl, Porton Down, Salisbury SP40JQ, Wilts, England

来源：

ACM COMPUTING SURVEYS | 2024年 / 56卷 / 05期

关键词：

Deep reinforcement learning; DRL; Explainable AI; XAI; neural networks; Survey; Review;

D O I：

10.1145/3623377

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

The use of Deep Reinforcement Learning (DRL) schemes has increased dramatically since their first introduction in 2015. Though uses in many different applications are being found, they still have a problem with the lack of interpretability. This has bread a lack of understanding and trust in the use of DRL solutions from researchers and the general public. To solve this problem, the field of Explainable Artificial Intelligence has emerged. This entails a variety of different methods that look to open the DRL black boxes, ranging from the use of interpretable symbolic Decision Trees to numerical methods like Shapley Values. This review looks at which methods are being used and for which applications. This is done to identify which models are the best suited to each application or if a method is being underutilised.

引用

页数：35

共 50 条

[11] HEX: Human-in-the-loop explainability via deep reinforcement learning [J].

Lash, Michael T. .

DECISION SUPPORT SYSTEMS, 2024, 187

[12] Review on Applications of Deep Reinforcement Learning in Regulation of Microgrid Systems [J].

Zhang Y. ;

Lin Y. ;

Huang G. ;

Yang X. ;

Weng G. ;

Zhou Z. .

Dianwang Jishu/Power System Technology, 2023, 47 (07) :2775-2787

[13] Contrastive Learning Methods for Deep Reinforcement Learning [J].

Wang, Di ;

Hu, Mengqi .

IEEE ACCESS, 2023, 11 :97107-97117

[14] Deep Reinforcement Learning for Power System Applications: An Overview [J].

Zhang, Zidong ;

Zhang, Dongxia ;

Qiu, Robert C. .

CSEE JOURNAL OF POWER AND ENERGY SYSTEMS, 2020, 6 (01) :213-225

[15] Deep Reinforcement Learning with Applications in Transportation [J].

Qin, Zhiwei ;

Tang, Jian ;

Ye, Jieping .

KDD'19: PROCEEDINGS OF THE 25TH ACM SIGKDD INTERNATIONAL CONFERENCCE ON KNOWLEDGE DISCOVERY AND DATA MINING, 2019, :3201-3202

[16] Testing Reinforcement Learning Explainability Methods in a Multi-Agent Cooperative Environment [J].

Domenech i Vila, Marc ;

Gnatyshak, Dmitry ;

Tormos, Adrian ;

Alvarez-Napagao, Sergio .

ARTIFICIAL INTELLIGENCE RESEARCH AND DEVELOPMENT, 2022, 356 :355-364

[17] Reproducibility and Explainability of Deep Learning in Mammography: A Systematic Review of Literature [J].

Bhalla, Deeksha ;

Rangarajan, Krithika ;

Chandra, Tany ;

Banerjee, Subhashis ;

Arora, Chetan .

INDIAN JOURNAL OF RADIOLOGY AND IMAGING, 2024, 34 (03) :469-487

[18] Deep reinforcement learning in medical imaging: A literature review [J].

Zhou, S. Kevin ;

Le, Hoang Ngan ;

Luu, Khoa ;

Nguyen, Hien, V ;

Ayache, Nicholas .

MEDICAL IMAGE ANALYSIS, 2021, 73

[19] A Review of Deep Learning Methods and Applications for Unmanned Aerial Vehicles [J].

Carrio, Adrian ;

Sampedro, Carlos ;

Rodriguez-Ramos, Alejandro ;

Campoy, Pascual .

JOURNAL OF SENSORS, 2017, 2017

[20] Deep reinforcement learning in chemistry: A review [J].

Sridharan, Bhuvanesh ;

Sinha, Animesh ;

Bardhan, Jai ;

Modee, Rohit ;

Ehara, Masahiro ;

Priyakumar, U. Deva .

JOURNAL OF COMPUTATIONAL CHEMISTRY, 2024, 45 (22) :1886-1898

← 1 2 3 4 5 →